1 option
Deep Learning to See : Towards New Foundations of Computer Vision / by Alessandro Betti, Marco Gori, Stefano Melacci.
- Format:
- Book
- Author/Creator:
- Betti, Alessandro., Author.
- Gori, Marco, Author.
- Melacci, Stefano., Author.
- Series:
- Computer Science (SpringerNature-11645)
- SpringerBriefs in computer science 2191-5776
- SpringerBriefs in Computer Science, 2191-5776
- Language:
- English
- Subjects (All):
- Computer vision.
- Machine learning.
- Computational neuroscience.
- Color.
- Vision.
- Computer Vision.
- Machine Learning.
- Computational Neuroscience.
- Vision and Colour Science.
- Local Subjects:
- Computer Vision.
- Machine Learning.
- Computational Neuroscience.
- Vision and Colour Science.
- Physical Description:
- 1 online resource (XIV, 105 pages) : 13 illustrations, 3 illustrations in color.
- Edition:
- 1st ed. 2022.
- Contained In:
- Springer Nature eBook
- Place of Publication:
- Cham : Springer International Publishing : Imprint: Springer, 2022.
- System Details:
- text file PDF
- Summary:
- The remarkable progress in computer vision over the last few years is, by and large, attributed to deep learning, fueled by the availability of huge sets of labeled data, and paired with the explosive growth of the GPU paradigm. While subscribing to this view, this book criticizes the supposed scientific progress in the field, and proposes the investigation of vision within the framework of information-based laws of nature. Specifically, the present work poses fundamental questions about vision that remain far from understood, leading the reader on a journey populated by novel challenges resonating with the foundations of machine learning. The central thesis is that for a deeper understanding of visual computational processes, it is necessary to look beyond the applications of general purpose machine learning algorithms, and focus instead on appropriate learning theories that take into account the spatiotemporal nature of the visual signal. Topics and features: Presents a curiosity-driven approach, posing questions to stimulate readers to design novel computational models of vision Offers a rethinking of computer vision, arguing for an approach based on vision in nature, versus regarding visual signals as collections of images Provides an interdisciplinary commentary, aiming to unify computer vision, machine learning, human vision, and computational neuroscience Serving to inspire and stimulate critical reflection and discussion, yet requiring no prior advanced technical knowledge, the text can naturally be paired with classic textbooks on computer vision to better frame the current state of the art, open problems, and novel potential solutions. This unique volume will be of great benefit to graduate and advanced undergraduate students in computer science, computational neuroscience, physics, and other related disciplines.
- Contents:
- 1. Introduction
- 2. Cutting the Umbilical Cord with Pattern Recognition
- 3. Spatiotemporal Visual Environments
- 4. Hierarchical Description of Visual Tasks
- 5. Benchmarks and the "En Plein Air" Challenge.
- Other Format:
- Printed edition:
- ISBN:
- 978-3-030-90987-1
- 9783030909871
- Access Restriction:
- Restricted for use by site license.
The Penn Libraries is committed to describing library materials using current, accurate, and responsible language. If you discover outdated or inaccurate language, please fill out this feedback form to report it and suggest alternative language.